KaLM-Reranker-V1: Fast but Not Late Interaction for Compressed Document Reranking
KaLM-Reranker-V1 is a fast reranker that decouples query and passage computation using encoder-decoder architecture with Matryoshka embedding pooling and cross-attention for effici…
Hugging Face · Daily Papers
·Xinping Zhao, Jiaxin Xu
·
·▲ 38 upvotes
Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.
Autores: Xinping Zhao, Jiaxin Xu, Ziqi Dai, Xin Zhang, Shouzheng Huang, Danyu Tang
- 38 upvotes da comunidade
- Temas: reranker, encoder-decoder architecture, Matryoshka embedding pooling, cross-attention, late-interaction, parameter-efficient fine-tuning
Resumo
Resumo original (em inglês), extraído do paper:
KaLM-Reranker-V1 is a fast reranker that decouples query and passage computation using encoder-decoder architecture with Matryoshka embedding pooling and cross-attention for efficient relevance modeling.
// relacionados
Leia também
Editorial
DataClaw0: a lapidação dos dados vira tarefa de aprendizado
Blog
OpenAI says new GPT-5.5-Cyber outperforms Anthropic's Mythos on cybersecurity benchmark
Blog
Top spy agencies say AI cyber threats will impact you within months. Here’s why
Blog